My main research interests are Natural Language Processing (both NLU and NLG) and Reinforcement Learning (especially Deep Learning combined with Monte-Carlo methods). I am aware of the potential risks behind Artificial Intelligence, so I am firmly convinced that mitigating and anticipating them is one of the most important challenges in the field. Hence, I am very interested in the ethical aspects of AI development, such as AI-alignment, fairness and privacy-preserving models.